Abstract
While various linear and nonlinear forecasting models exist, multivariate methods like VAR, Exponential smoothing, and Box-Jenkins’ ARIMA methodology constitute the widely used methods in time series. This paper employs series of Turkish private consumption, exports and GDP data ranging between 1998: Q1 and 2017: Q4 to analyze the forecast performance of the three models using measures of accuracy such as RMSE, MAE, MAPE, Theil’s & . Seasonal decomposition and ADF unit root tests were performed to obtain new deseasonalized series and stationarity, respectively. Results offer preference for the use of ARIMA in forecasting, having performed better than VAR and exponential smoothing in all scenarios. Additionally, VAR model provided better forecast accuracy than exponential smoothing on all measures of accuracy except on Thiel’s whose VAR values were not computed. Cautionary use of ARIMA for forecasting is recommended. Keywords: Forecast Evaluation, ARIMA, Exponential Smoothing, VAR JEL Classifications: C1, E00, C51 DOI: https://doi.org/10.32479/ijefi.9020
Highlights
Tracking the overtime evolutionary path of economic variables and making forward projections help policymakers in setting, predicting and achieving both microeconomics and macroeconomic targets. This process is achieved through various univariate and multivariate forecasting methods such as the Box-Jenkins’ ARIMA, exponential smoothing and Vector Autoregressive (VAR) models
The I component indicates the integral number of the series, which is the number of times a series has to be differenced to be stationary
We observe that the respective root mean square error (RMSE) and MAE of the ARIMA model (0.038945 and 0.029059 for dln_consa, 0.079034 and 0.067008 for dln_expsa and 0.045760 and 0.030414 for dln_gdpsa) are much lower than the respective RMSE and MAE values for the VAR (0.046662 and 0.033823 for dln_consa, 0.090192 and 0.065262 for dln_expsa and 0.047286 and 0.034870 for dln_gdpsa) and exponential smoothing (0.067013 and 0.047326 for dln_consa, 0.101399 and 0.069019 for dln_expsa and 0.076805 and 0.052021 for dln_gdpsa)
Summary
Tracking the overtime evolutionary path of economic variables and making forward projections help policymakers in setting, predicting and achieving both microeconomics and macroeconomic targets. This process is achieved through various univariate and multivariate forecasting methods such as the Box-Jenkins’ ARIMA, exponential smoothing and Vector Autoregressive (VAR) models. Exponential smoothing is a method that allocate weights to different series to account for fluctuations in the data. This paper, makes use of quarterly data series of the Turkish Private Consumption, Exports and GDP data ranging from 1998 Q1-2017 Q4 to undertake a comparative evaluation of the widely used time series forecasting methods of ARIMA, Exponential smoothing, and VAR to choose the best method to follow. The sections discuss literature, data, methodology, results, and conclusions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Economics and Financial Issues
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
